© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 693
    Prev
    Next
    INDEX
    Explanations

    parts of code, especially around parentheses and braces

    oai_token-act-pair · gemini-2.0-flash

    code keywords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rich
    -0.53
    dsi
    -0.47
    rilla
    -0.47
     суток
    -0.46
    설
    -0.45
     Lo
    -0.44
     pose
    -0.44
     Enf
    -0.44
     poses
    -0.43
    antit
    -0.42
    POSITIVE LOGITS
     Numerology
    0.65
     Protección
    0.65
     crdi
    0.61
     fometimes
    0.60
     cohomology
    0.59
    oredCriteria
    0.59
    InsertCommand
    0.57
     commutation
    0.57
    شهاد
    0.56
    Tikang
    0.56
    Activations Density 0.589%

    No Known Activations